Korean-Speaking AI Personalization Response Evaluator

You will help evaluate AI personalization by creating Korean conversations that include personal context and reviewing how well AI systems respond. Your feedback will help assess whether responses are grounded, natural, useful, and free from unsupported inferences.

• Create and run multi-turn prompts in Korean using personal context.
• Review responses for grounding, appropriate use of context, naturalness, helpfulness, and incorrect inferences.
• Compare AI responses side by side and identify subtle differences in quality.
• Check relevant debug information during evaluations.
• Write evidence-based rationales that reference specific conversation turns.
• Add detailed annotations and maintain consistent quality across repeated review tasks.

What It Pays and Takes

This is a part-time remote contractor role for an intermediate-level contributor. Experience with prompt design, AI quality evaluation, data annotation, content moderation, or a related analytical field is preferred.

• $15 per hour.
• 20+ hours per week.
• Remote work open worldwide.
• Strong Korean reading and writing ability.
• Excellent analytical thinking, attention to detail, and written communication skills.
• Ability to identify unsupported claims, forced connections, and subtle response-quality differences.
• Ability to follow detailed project guidelines and work independently.
• A relevant degree or equivalent experience is welcome.

How It Works

Apply on OpenTrain with your resume and then complete the application on the hiring site.

About AI Training Work

AI training is the human work behind systems that learn from examples, including writing prompts and rating model responses. People with strong language, analytical, or subject knowledge help make these systems more accurate and useful.